Merge branch 'main' into empty-object-with-newline

pre_commit_hooks/check_added_large_files.py

@@ -4,7 +4,7 @@ import argparse
 import math
 import os
 import subprocess
-from typing import Sequence
+from collections.abc import Sequence
 
 from pre_commit_hooks.util import added_files
 from pre_commit_hooks.util import zsplit
@@ -46,7 +46,7 @@ def find_large_added_files(
         filenames_filtered &= added_files()
 
     for filename in filenames_filtered:
-        kb = int(math.ceil(os.stat(filename).st_size / 1024))
+        kb = math.ceil(os.stat(filename).st_size / 1024)
         if kb > maxkb:
             print(f'{filename} ({kb} KB) exceeds {maxkb} KB.')
             retv = 1

pre_commit_hooks/check_ast.py

@@ -5,7 +5,7 @@ import ast
 import platform
 import sys
 import traceback
-from typing import Sequence
+from collections.abc import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/check_builtin_literals.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import ast
+from collections.abc import Sequence
 from typing import NamedTuple
-from typing import Sequence
 
 
 BUILTIN_TYPES = {

pre_commit_hooks/check_byte_order_marker.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import argparse
-from typing import Sequence
+from collections.abc import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/check_case_conflict.py

@@ -1,9 +1,9 @@
 from __future__ import annotations
 
 import argparse
-from typing import Iterable
-from typing import Iterator
-from typing import Sequence
+from collections.abc import Iterable
+from collections.abc import Iterator
+from collections.abc import Sequence
 
 from pre_commit_hooks.util import added_files
 from pre_commit_hooks.util import cmd_output

pre_commit_hooks/check_docstring_first.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import argparse
 import io
 import tokenize
+from collections.abc import Sequence
 from tokenize import tokenize as tokenize_tokenize
-from typing import Sequence
 
 NON_CODE_TOKENS = frozenset((
     tokenize.COMMENT, tokenize.ENDMARKER, tokenize.NEWLINE, tokenize.NL,

pre_commit_hooks/check_executables_have_shebangs.py

@@ -4,9 +4,9 @@ from __future__ import annotations
 import argparse
 import shlex
 import sys
-from typing import Generator
+from collections.abc import Generator
+from collections.abc import Sequence
 from typing import NamedTuple
-from typing import Sequence
 
 from pre_commit_hooks.util import cmd_output
 from pre_commit_hooks.util import zsplit
@@ -35,7 +35,7 @@ class GitLsFile(NamedTuple):
     filename: str
 
 
-def git_ls_files(paths: Sequence[str]) -> Generator[GitLsFile, None, None]:
+def git_ls_files(paths: Sequence[str]) -> Generator[GitLsFile]:
     outs = cmd_output('git', 'ls-files', '-z', '--stage', '--', *paths)
     for out in zsplit(outs):
         metadata, filename = out.split('\t')

pre_commit_hooks/check_json.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import json
+from collections.abc import Sequence
 from typing import Any
-from typing import Sequence
 
 
 def raise_duplicate_keys(

pre_commit_hooks/check_merge_conflict.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import os.path
-from typing import Sequence
+from collections.abc import Sequence
 
 from pre_commit_hooks.util import cmd_output
 

pre_commit_hooks/check_shebang_scripts_are_executable.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import argparse
 import shlex
 import sys
-from typing import Sequence
+from collections.abc import Sequence
 
 from pre_commit_hooks.check_executables_have_shebangs import EXECUTABLE_VALUES
 from pre_commit_hooks.check_executables_have_shebangs import git_ls_files
@@ -36,7 +36,7 @@ def _message(path: str) -> None:
         f'`chmod +x {shlex.quote(path)}`\n'
         f'  If on Windows, you may also need to: '
         f'`git add --chmod=+x {shlex.quote(path)}`\n'
-        f'  If it not supposed to be executable, double-check its shebang '
+        f'  If it is not supposed to be executable, double-check its shebang '
         f'is wanted.\n',
         file=sys.stderr,
     )

pre_commit_hooks/check_symlinks.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import os.path
-from typing import Sequence
+from collections.abc import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/check_toml.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import sys
-from typing import Sequence
+from collections.abc import Sequence
 
 if sys.version_info >= (3, 11):  # pragma: >=3.11 cover
     import tomllib

pre_commit_hooks/check_vcs_permalinks.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import argparse
 import re
 import sys
-from typing import Pattern
-from typing import Sequence
+from collections.abc import Sequence
+from re import Pattern
 
 
 def _get_pattern(domain: str) -> Pattern[bytes]:

pre_commit_hooks/check_xml.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import xml.sax.handler
-from typing import Sequence
+from collections.abc import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/check_yaml.py

@@ -1,17 +1,17 @@
 from __future__ import annotations
 
 import argparse
+from collections.abc import Generator
+from collections.abc import Sequence
 from typing import Any
-from typing import Generator
 from typing import NamedTuple
-from typing import Sequence
 
 import ruamel.yaml
 
 yaml = ruamel.yaml.YAML(typ='safe')
 
 
-def _exhaust(gen: Generator[str, None, None]) -> None:
+def _exhaust(gen: Generator[str]) -> None:
     for _ in gen:
         pass
 
@@ -46,7 +46,7 @@ def main(argv: Sequence[str] | None = None) -> int:
         '--unsafe', action='store_true',
         help=(
             'Instead of loading the files, simply parse them for syntax.  '
-            'A syntax-only check enables extensions and unsafe contstructs '
+            'A syntax-only check enables extensions and unsafe constructs '
             'which would otherwise be forbidden.  Using this option removes '
             'all guarantees of portability to other yaml implementations.  '
             'Implies --allow-multiple-documents'

pre_commit_hooks/debug_statement_hook.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import argparse
 import ast
 import traceback
+from collections.abc import Sequence
 from typing import NamedTuple
-from typing import Sequence
 
 
 DEBUG_STATEMENTS = {

pre_commit_hooks/destroyed_symlinks.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import argparse
 import shlex
 import subprocess
-from typing import Sequence
+from collections.abc import Sequence
 
 from pre_commit_hooks.util import cmd_output
 from pre_commit_hooks.util import zsplit

pre_commit_hooks/detect_aws_credentials.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import argparse
 import configparser
 import os
+from collections.abc import Sequence
 from typing import NamedTuple
-from typing import Sequence
 
 
 class BadFile(NamedTuple):

pre_commit_hooks/detect_private_key.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import argparse
-from typing import Sequence
+from collections.abc import Sequence
 
 BLACKLIST = [
     b'BEGIN RSA PRIVATE KEY',

pre_commit_hooks/end_of_file_fixer.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import os
+from collections.abc import Sequence
 from typing import IO
-from typing import Sequence
 
 
 def fix_file(file_obj: IO[bytes]) -> int:

pre_commit_hooks/file_contents_sorter.py

@@ -12,11 +12,11 @@ conflicts and keep the file nicely ordered.
 from __future__ import annotations
 
 import argparse
+from collections.abc import Iterable
+from collections.abc import Sequence
 from typing import Any
 from typing import Callable
 from typing import IO
-from typing import Iterable
-from typing import Sequence
 
 PASS = 0
 FAIL = 1
@@ -54,18 +54,21 @@ def sort_file_contents(
 def main(argv: Sequence[str] | None = None) -> int:
     parser = argparse.ArgumentParser()
     parser.add_argument('filenames', nargs='+', help='Files to sort')
-    parser.add_argument(
+
+    mutex = parser.add_mutually_exclusive_group(required=False)
+    mutex.add_argument(
         '--ignore-case',
         action='store_const',
         const=bytes.lower,
         default=None,
         help='fold lower case to upper case characters',
     )
-    parser.add_argument(
+    mutex.add_argument(
         '--unique',
         action='store_true',
         help='ensure each line is unique',
     )
+
     args = parser.parse_args(argv)
 
     retv = PASS

pre_commit_hooks/fix_byte_order_marker.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import argparse
-from typing import Sequence
+from collections.abc import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/fix_encoding_pragma.py

@@ -1,9 +1,10 @@
 from __future__ import annotations
 
 import argparse
+import sys
+from collections.abc import Sequence
 from typing import IO
 from typing import NamedTuple
-from typing import Sequence
 
 DEFAULT_PRAGMA = b'# -*- coding: utf-8 -*-'
 
@@ -107,6 +108,13 @@ def _normalize_pragma(pragma: str) -> bytes:
 
 
 def main(argv: Sequence[str] | None = None) -> int:
+    print(
+        'warning: this hook is deprecated and will be removed in a future '
+        'release because py2 is EOL. instead, use '
+        'https://github.com/asottile/pyupgrade',
+        file=sys.stderr,
+    )
+
     parser = argparse.ArgumentParser(
         'Fixes the encoding pragma of python files',
     )

pre_commit_hooks/forbid_new_submodules.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import os
-from typing import Sequence
+from collections.abc import Sequence
 
 from pre_commit_hooks.util import cmd_output
 

pre_commit_hooks/mixed_line_ending.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import collections
-from typing import Sequence
+from collections.abc import Sequence
 
 
 CRLF = b'\r\n'

pre_commit_hooks/no_commit_to_branch.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import re
+from collections.abc import Sequence
 from typing import AbstractSet
-from typing import Sequence
 
 from pre_commit_hooks.util import CalledProcessError
 from pre_commit_hooks.util import cmd_output

pre_commit_hooks/pretty_format_json.py

@@ -4,9 +4,9 @@ import argparse
 import json
 import re
 import sys
+from collections.abc import Mapping
+from collections.abc import Sequence
 from difflib import unified_diff
-from typing import Mapping
-from typing import Sequence
 
 def _insert_linebreaks(json_str: str) -> str:
     return re.sub(
@@ -135,17 +135,22 @@ def main(argv: Sequence[str] | None = None) -> int:
                 f'Input File {json_file} is not a valid JSON, consider using '
                 f'check-json',
             )
-            return 1
-
-        if contents != pretty_contents:
             status = 1
-            if args.autofix:
-                _autofix(json_file, pretty_contents)
-                if args.empty_object_with_newline:
-                    status = 0
-            else:
-                diff_output = get_diff(contents, pretty_contents, json_file)
-                sys.stdout.buffer.write(diff_output.encode())
+        else:
+            if contents != pretty_contents:
+                if args.autofix:
+                    _autofix(json_file, pretty_contents)
+                    if args.empty_object_with_newline:
+                        status = 0
+                else:
+                    diff_output = get_diff(
+                        contents,
+                        pretty_contents,
+                        json_file
+                    )
+                    sys.stdout.buffer.write(diff_output.encode())
+
+                status = 1
 
     return status
 

pre_commit_hooks/removed.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import sys
-from typing import Sequence
+from collections.abc import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/requirements_txt_fixer.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import re
+from collections.abc import Sequence
 from typing import IO
-from typing import Sequence
 
 
 PASS = 0
@@ -45,6 +45,11 @@ class Requirement:
         elif requirement.value == b'\n':
             return False
         else:
+            # if 2 requirements have the same name, the one with comments
+            # needs to go first (so that when removing duplicates, the one
+            # with comments is kept)
+            if self.name == requirement.name:
+                return bool(self.comments) > bool(requirement.comments)
             return self.name < requirement.name
 
     def is_complete(self) -> bool:
@@ -110,13 +115,20 @@ def fix_requirements(f: IO[bytes]) -> int:
     # which is automatically added by broken pip package under Debian
     requirements = [
         req for req in requirements
-        if req.value != b'pkg-resources==0.0.0\n'
+        if req.value not in [
+            b'pkg-resources==0.0.0\n',
+            b'pkg_resources==0.0.0\n',
+        ]
     ]
 
+    # sort the requirements and remove duplicates
+    prev = None
     for requirement in sorted(requirements):
         after.extend(requirement.comments)
         assert requirement.value, requirement.value
-        after.append(requirement.value)
+        if prev is None or requirement.value != prev.value:
+            after.append(requirement.value)
+            prev = requirement
     after.extend(rest)
 
     after_string = b''.join(after)

pre_commit_hooks/sort_simple_yaml.py

@@ -20,7 +20,7 @@ complicated YAML files.
 from __future__ import annotations
 
 import argparse
-from typing import Sequence
+from collections.abc import Sequence
 
 
 QUOTES = ["'", '"']

pre_commit_hooks/string_fixer.py

@@ -3,8 +3,15 @@ from __future__ import annotations
 import argparse
 import io
 import re
+import sys
 import tokenize
-from typing import Sequence
+from collections.abc import Sequence
+
+if sys.version_info >= (3, 12):  # pragma: >=3.12 cover
+    FSTRING_START = tokenize.FSTRING_START
+    FSTRING_END = tokenize.FSTRING_END
+else:  # pragma: <3.12 cover
+    FSTRING_START = FSTRING_END = -1
 
 START_QUOTE_RE = re.compile('^[a-zA-Z]*"')
 
@@ -40,11 +47,17 @@ def fix_strings(filename: str) -> int:
     # Basically a mutable string
     splitcontents = list(contents)
 
+    fstring_depth = 0
+
     # Iterate in reverse so the offsets are always correct
     tokens_l = list(tokenize.generate_tokens(io.StringIO(contents).readline))
     tokens = reversed(tokens_l)
     for token_type, token_text, (srow, scol), (erow, ecol), _ in tokens:
-        if token_type == tokenize.STRING:
+        if token_type == FSTRING_START:  # pragma: >=3.12 cover
+            fstring_depth += 1
+        elif token_type == FSTRING_END:  # pragma: >=3.12 cover
+            fstring_depth -= 1
+        elif fstring_depth == 0 and token_type == tokenize.STRING:
             new_text = handle_match(token_text)
             splitcontents[
                 line_offsets[srow] + scol:

pre_commit_hooks/tests_should_end_in_test.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import argparse
 import os.path
 import re
-from typing import Sequence
+from collections.abc import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/trailing_whitespace_fixer.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import os
-from typing import Sequence
+from collections.abc import Sequence
 
 
 def _fix_file(